© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 78816
    Prev
    Next
    INDEX
    Explanations

    gather, here, stand, today, tonight, around

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_29_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    财政
    0.33
    <\
    0.31
     Pour
    0.30
    graf
    0.30
     Ez
    0.30
    Em
    0.30
    Pour
    0.30
    বেদন
    0.29
     삽
    0.29
    Breath
    0.29
    POSITIVE LOGITS
     বেশকিছু
    0.34
     ziemlich
    0.33
     الاجتما
    0.32
     occasionally
    0.32
     Occasionally
    0.31
     somewhat
    0.31
     manly
    0.31
     கிட்டத்தட்ட
    0.30
    رجال
    0.30
     manchmal
    0.30
    Activations Density 0.005%

    No Known Activations